Triple
T17873222
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Poul Gnatt |
E446885
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Poul Gnatt |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Poul Gnatt | Statement: [Poul Gnatt, name, Poul Gnatt]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Poul Gnatt Context triple: [Poul Gnatt, name, Poul Gnatt]
-
A.
Poul Gnatt
chosen
Poul Gnatt was a Danish-born ballet dancer and artistic director who played a pivotal role in establishing and developing professional ballet in New Zealand.
-
B.
Peter Funt
Peter Funt is an American television personality and producer best known for hosting and continuing his father Allen Funt’s hidden-camera show "Candid Camera."
-
C.
Raymond Babbitt
Raymond Babbitt is a socially withdrawn autistic savant with extraordinary mathematical and memory abilities, best known as Dustin Hoffman's character in the film "Rain Man."
-
D.
George Zames
George Zames was a prominent control theorist known for his foundational contributions to robust control and H-infinity methods in systems engineering.
-
E.
Peder Sather
Peder Sather was a 19th-century Norwegian-born American banker and philanthropist known for his significant financial support of the University of California, Berkeley.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d8b9f4c22c819093c2680434472894 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e49aa4959881908774dafb7be99191 |
completed | April 19, 2026, 9:04 a.m. |
Created at: April 10, 2026, 10:18 a.m.